Artificial intelligence and radiomics in pulmonary nodule management: current status and future applications

CT-based whole lung radiomics nomogram: a tool for identifying the risk of cardiovascular disease in patients with chronic obstructive pulmonary disease

OBJECTIVES

To evaluate the value of CT-based whole lung radiomics nomogram for identifying the risk of cardiovascular disease (CVD) in patients with chronic obstructive pulmonary disease (COPD).

MATERIALS AND METHODS

A total of 974 patients with COPD were divided into a training cohort (n = 402), an internal validation cohort (n = 172), and an external validation cohort (n = 400) from three hospitals. Clinical data and CT findings were analyzed. Radiomics features of whole lung were extracted from the non-contrast chest CT images. A radiomics signature was constructed with algorithms. Combined with the radiomics score and independent clinical factors, multivariate logistic regression analysis was used to establish a radiomics nomogram. ROC curve was used to analyze the prediction performance of the model.

RESULTS

Age, weight, and GOLD were the independent clinical factors. A total of 1218 features were extracted and reduced to 15 features to build the radiomics signature. In the training cohort, the combined model (area under the curve [AUC], 0.731) showed better discrimination capability (p < 0.001) than the clinical factors model (AUC, 0.605). In the internal validation cohort, the combined model (AUC, 0.727) performed better (p = 0.032) than the clinical factors model (AUC, 0.629). In the external validation cohort, the combined model (AUC, 0.725) performed better (p < 0.001) than the clinical factors model (AUC, 0.690). Decision curve analysis demonstrated the radiomics nomogram outperformed the clinical factors model.

CONCLUSION

The CT-based whole lung radiomics nomogram has the potential to identify the risk of CVD in patients with COPD.

CLINICAL RELEVANCE STATEMENT

This study helps to identify cardiovascular disease risk in patients with chronic obstructive pulmonary disease on chest CT scans.

KEY POINTS

• To investigate the value of CT-based whole lung radiomics features in identifying the risk of cardiovascular disease in chronic obstructive pulmonary disease patients. • The radiomics nomogram showed better performance than the clinical factors model to identify the risk of cardiovascular disease in patients with chronic obstructive pulmonary disease. • The radiomics nomogram demonstrated excellent performance in the training, internal validation, and external validation cohort (AUC, 0.731; AUC, 0.727; AUC, 0.725).

Artificial intelligence-based graded training of pulmonary nodules for junior radiology residents and medical imaging students

BACKGROUND

To evaluate the efficiency of artificial intelligence (AI)-assisted diagnosis system in the pulmonary nodule detection and diagnosis training of junior radiology residents and medical imaging students.

METHODS

The participants were divided into three groups. Medical imaging students of Grade 2020 in the Jinzhou Medical University were randomly divided into Groups 1 and 2; Group 3 comprised junior radiology residents. Group 1 used the traditional case-based teaching mode; Groups 2 and 3 used the 'AI intelligent assisted diagnosis system' teaching mode. All participants performed localisation, grading and qualitative diagnosed of 1,057 lung nodules in 420 cases for seven rounds of testing after training. The sensitivity and number of false positive nodules in different densities (solid, pure ground glass, mixed ground glass and calcification), sizes (less than 5 mm, 5-10 mm and over 10 mm) and positions (subpleural, peripheral and central) of the pulmonary nodules in the three groups were detected. The pathological results and diagnostic opinions of radiologists formed the criteria. The detection rate, diagnostic compliance rate, false positive number/case, and kappa scores of the three groups were compared.

RESULTS

There was no statistical difference in baseline test scores between Groups 1 and 2, and there were statistical differences with Group 3 (P = 0.036 and 0.011). The detection rate of solid, pure ground glass and calcified nodules; small-, medium-, and large-diameter nodules; and peripheral nodules were significantly different among the three groups (P<0.05). After seven rounds of training, the diagnostic compliance rate increased in all three groups, with the largest increase in Group 2. The average kappa score increased from 0.508 to 0.704. The average kappa score for Rounds 1-4 and 5-7 were 0.595 and 0.714, respectively. The average kappa scores of Groups 1,2 and 3 increased from 0.478 to 0.658, 0.417 to 0.757, and 0.638 to 0.791, respectively.

CONCLUSION

The AI assisted diagnosis system is a valuable tool for training junior radiology residents and medical imaging students to perform pulmonary nodules detection and diagnosis.

Artificial intelligence-driven computer aided diagnosis system provides similar diagnosis value compared with doctors' evaluation in lung cancer screening

OBJECTIVE

To evaluate the consistency between doctors and artificial intelligence (AI) software in analysing and diagnosing pulmonary nodules, and assess whether the characteristics of pulmonary nodules derived from the two methods are consistent for the interpretation of carcinomatous nodules.

MATERIALS AND METHODS

This retrospective study analysed participants aged 40-74 in the local area from 2011 to 2013. Pulmonary nodules were examined radiologically using a low-dose chest CT scan, evaluated by an expert panel of doctors in radiology, oncology, and thoracic departments, as well as a computer-aided diagnostic(CAD) system based on the three-dimensional(3D) convolutional neural network (CNN) with DenseNet architecture(InferRead CT Lung, IRCL). Consistency tests were employed to assess the uniformity of the radiological characteristics of the pulmonary nodules. The receiver operating characteristic (ROC) curve was used to evaluate the diagnostic accuracy. Logistic regression analysis is utilized to determine whether the two methods yield the same predictive factors for cancerous nodules.

RESULTS

A total of 570 subjects were included in this retrospective study. The AI software demonstrated high consistency with the panel's evaluation in determining the position and diameter of the pulmonary nodules (kappa = 0.883, concordance correlation coefficient (CCC) = 0.809, p = 0.000). The comparison of the solid nodules' attenuation characteristics also showed acceptable consistency (kappa = 0.503). In patients diagnosed with lung cancer, the area under the curve (AUC) for the panel and AI were 0.873 (95%CI: 0.829-0.909) and 0.921 (95%CI: 0.884-0.949), respectively. However, there was no significant difference (p = 0.0950). The maximum diameter, solid nodules, subsolid nodules were the crucial factors for interpreting carcinomatous nodules in the analysis of expert panel and IRCL pulmonary nodule characteristics.

CONCLUSION

AI software can assist doctors in diagnosing nodules and is consistent with doctors' evaluations and diagnosis of pulmonary nodules.

Intelligent diagnosis of lung nodule images based on machine learning in the context of lung teaching

The vast majority of intelligent diagnosis models have widespread problems, which seriously affect the medical staff judgment of patients' injuries. So depending on the situation, you need to use different algorithms, The study suggests a model for intelligent diagnosis of lung nodule images based on machine learning, and a support vector machine-based machine learning algorithm is selected. In order to improve the diagnostic accuracy of intelligent diagnosis of lung nodule images as well as the diagnostic model of lung nodule images. The objectives are broken down into algorithm determination and model construction, and the proposed optimized model is solved using machine learning techniques in order to achieve the original algorithm selected for intelligent diagnosis of lung nodule photos. The validation findings demonstrated that dimensionality reduction of the features produced 17 × 1120 and 17 × 2980 non-node matrices with 1216 nodes and 3407 non-nodes in 17 features. The support vector machine classification method has more benefits in terms of accuracy, sensitivity, and specificity when compared to other classification methods. Since there were some anomalies among both benign and malignant tumors and no discernible difference between them, the distribution of median values revealed that the data was symmetrical in terms of texture and gray scale. Non-small nodules can be identified from benign nodules, but more training is needed to separate them from the other 2 types. Pulmonary nodules are a common disease. MN are distinct from the other 2 types, non-small nodules and benign small nodules, which require further training to differentiate. This has great practical value in teaching practice. Therefore, building a machine learning-based intelligent diagnostic model for pulmonary nodules is of significant importance in helping to solve medical imaging diagnostic problems.

Radiomics and artificial intelligence for risk stratification of pulmonary nodules: Ready for primetime?

Pulmonary nodules are ubiquitously found on computed tomography (CT) imaging either incidentally or via lung cancer screening and require careful diagnostic evaluation and management to both diagnose malignancy when present and avoid unnecessary biopsy of benign lesions. To engage in this complex decision-making, clinicians must first risk stratify pulmonary nodules to determine what the best course of action should be. Recent developments in imaging technology, computer processing power, and artificial intelligence algorithms have yielded radiomics-based computer-aided diagnosis tools that use CT imaging data including features invisible to the naked human eye to predict pulmonary nodule malignancy risk and are designed to be used as a supplement to routine clinical risk assessment. These tools vary widely in their algorithm construction, internal and external validation populations, intended-use populations, and commercial availability. While several clinical validation studies have been published, robust clinical utility and clinical effectiveness data are not yet currently available. However, there is reason for optimism as ongoing and future studies aim to target this knowledge gap, in the hopes of improving the diagnostic process for patients with pulmonary nodules.

Deep convolutional network-based chest radiographs screening model for pneumoconiosis

Background

Pneumoconiosis is the most important occupational disease all over the world, with high prevalence and mortality. At present, the monitoring of workers exposed to dust and the diagnosis of pneumoconiosis rely on manual interpretation of chest radiographs, which is subjective and low efficiency. With the development of artificial intelligence technology, a more objective and efficient computer aided system for pneumoconiosis diagnosis can be realized. Therefore, the present study reported a novel deep learning (DL) artificial intelligence (AI) system for detecting pneumoconiosis in digital frontal chest radiographs, based on which we aimed to provide references for radiologists.

Methods

We annotated 49,872 chest radiographs from patients with pneumoconiosis and workers exposed to dust using a self-developed tool. Next, we used the labeled images to train a convolutional neural network (CNN) algorithm developed for pneumoconiosis screening. Finally, the performance of the trained pneumoconiosis screening model was validated using a validation set containing 495 chest radiographs.

Results

Approximately, 51% (25,435/49,872) of the chest radiographs were labeled as normal. Pneumoconiosis was detected in 49% (24,437/49,872) of the labeled radiographs, among which category-1, category-2, and category-3 pneumoconiosis accounted for 53.1% (12,967/24,437), 20.4% (4,987/24,437), and 26.5% (6,483/24,437) of the patients, respectively. The CNN DL algorithm was trained using these data. The validation set of 495 digital radiography chest radiographs included 261 cases of pneumoconiosis and 234 cases of non-pneumoconiosis. As a result, the accuracy of the AI system for pneumoconiosis identification was 95%, the area under the curve was 94.7%, and the sensitivity was 100%.

Conclusion

DL algorithm based on CNN helped screen pneumoconiosis in the chest radiographs with high performance; thus, it could be suitable for diagnosing pneumoconiosis automatically and improve the efficiency of radiologists.

Diagnostic value of artificial intelligence based on computed tomography (CT) density in benign and malignant pulmonary nodules: a retrospective investigation

Objective

To evaluate the diagnostic value of artificial intelligence (AI) in the detection and management of benign and malignant pulmonary nodules (PNs) using computed tomography (CT) density.

Methods

A retrospective analysis was conducted on the clinical data of 130 individuals diagnosed with PNs based on pathological confirmation. The utilization of AI and physicians has been employed in the diagnostic process of distinguishing benign and malignant PNs. The CT images depicting PNs were integrated into AI-based software. The gold standard for evaluating the accuracy of AI diagnosis software and physician interpretation was the pathological diagnosis.

Results

Out of 226 PNs screened from 130 patients diagnosed by AI and physician reading based on CT, 147 were confirmed by pathology. AI had a sensitivity of 94.69% and radiologists had a sensitivity of 85.40% in identifying PNs. The chi-square analysis indicated that the screening capacity of AI was superior to that of physician reading, with statistical significance (p < 0.05). 195 of the 214 PNs suggested by AI were confirmed pathologically as malignant, and 19 were identified as benign; among the 29 PNs suggested by AI as low risk, 13 were confirmed pathologically as malignant, and 16 were identified as benign. From the physician reading, 193 PNs were identified as malignant, 183 were confirmed malignant by pathology, and 10 appeared benign. Physician reading also identified 30 low-risk PNs, 19 of which were pathologically malignant and 11 benign. The physician readings and AI had kappa values of 0.432 and 0.547, respectively. The physician reading and AI area under curves (AUCs) were 0.814 and 0.798, respectively. Both of the diagnostic techniques had worthy diagnostic value, as indicated by their AUCs of >0.7.

Conclusion

It is anticipated that the use of AI-based CT diagnosis in the detection of PNs would increase the precision in early detection of lung carcinoma, as well as yield more precise evidence for clinical management.

Biomedical Big Data Technologies, Applications, and Challenges for Precision Medicine: A Review

The explosive growth of biomedical Big Data presents both significant opportunities and challenges in the realm of knowledge discovery and translational applications within precision medicine. Efficient management, analysis, and interpretation of big data can pave the way for groundbreaking advancements in precision medicine. However, the unprecedented strides in the automated collection of large-scale molecular and clinical data have also introduced formidable challenges in terms of data analysis and interpretation, necessitating the development of novel computational approaches. Some potential challenges include the curse of dimensionality, data heterogeneity, missing data, class imbalance, and scalability issues. This overview article focuses on the recent progress and breakthroughs in the application of big data within precision medicine. Key aspects are summarized, including content, data sources, technologies, tools, challenges, and existing gaps. Nine fields-Datawarehouse and data management, electronic medical record, biomedical imaging informatics, Artificial intelligence-aided surgical design and surgery optimization, omics data, health monitoring data, knowledge graph, public health informatics, and security and privacy-are discussed.

The diagnosis performance of convolutional neural network in the detection of pulmonary nodules: a systematic review and meta-analysis

BACKGROUND

Pulmonary nodules are an early imaging indication of lung cancer, and early detection of pulmonary nodules can improve the prognosis of lung cancer. As one of the applications of machine learning, the convolutional neural network (CNN) applied to computed tomography (CT) imaging data improves the accuracy of diagnosis, but the results could be more consistent.

PURPOSE

To evaluate the diagnostic performance of CNN in assisting in detecting pulmonary nodules in CT images.

MATERIAL AND METHODS

PubMed, Cochrane Library, Web of Science, Elsevier, CNKI and Wanfang databases were systematically retrieved before 30 April 2023. Two reviewers searched and checked the full text of articles that might meet the criteria. The reference criteria are joint diagnoses by experienced physicians. The pooled sensitivity, specificity and the area under the summary receiver operating characteristic curve (AUC) were calculated by a random-effects model. Meta-regression analysis was performed to explore potential sources of heterogeneity.

RESULTS

Twenty-six studies were included in this meta-analysis, involving 2,391,702 regions of interest, comprising segmented images with a few wide pixels. The combined sensitivity and specificity values of the CNN model in detecting pulmonary nodules were 0.93 and 0.95, respectively. The pooled diagnostic odds ratio was 291. The AUC was 0.98. There was heterogeneity in sensitivity and specificity among the studies. The results suggested that data sources, pretreatment methods, reconstruction slice thickness, population source and locality might contribute to the heterogeneity of these eligible studies.

CONCLUSION

The CNN model can be a valuable diagnostic tool with high accuracy in detecting pulmonary nodules.

A pairwise radiomics algorithm-lesion pair relation estimation model for distinguishing multiple primary lung cancer from intrapulmonary metastasis

Background

Distinguishing multiple primary lung cancer (MPLC) from intrapulmonary metastasis (IPM) is critical for their disparate treatment strategy and prognosis. This study aimed to establish a non-invasive model to make the differentiation pre-operatively.

Methods

We retrospectively studied 168 patients with multiple lung cancers (307 pairs of lesions) including 118 cases for modeling and internal validation, and 50 cases for independent external validation. Radiomic features on computed tomography (CT) were extracted to calculate the absolute deviation of paired lesions. Features were then selected by correlation coefficients and random forest classifier 5-fold cross-validation, based on which the lesion pair relation estimation (PRE) model was developed. A major voting strategy was used to decide diagnosis for cases with multiple pairs of lesions. Cases from another institute were included as the external validation set for the PRE model to compete with two experienced clinicians.

Results

Seven radiomic features were selected for the PRE model construction. With major voting strategy, the mean area under receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the training versus internal validation versus external validation cohort to distinguish MPLC were 0.983 versus 0.844 versus 0.793, 0.942 versus 0.846 versus 0.760, 0.905 versus 0.728 versus 0.727, and 0.962 versus 0.910 versus 0.769, respectively. AUCs of the two clinicians were 0.619 and 0.580.

Conclusions

The CT radiomic feature-based lesion PRE model is potentially an accurate diagnostic tool for the differentiation of MPLC and IPM, which could help with clinical decision making.

A novel fusion algorithm for benign-malignant lung nodule classification on CT images

The accurate recognition of malignant lung nodules on CT images is critical in lung cancer screening, which can offer patients the best chance of cure and significant reductions in mortality from lung cancer. Convolutional Neural Network (CNN) has been proven as a powerful method in medical image analysis. Radiomics which is believed to be of interest based on expert opinion can describe high-throughput extraction from CT images. Graph Convolutional Network explores the global context and makes the inference on both graph node features and relational structures. In this paper, we propose a novel fusion algorithm, RGD, for benign-malignant lung nodule classification by incorporating Radiomics study and Graph learning into the multiple Deep CNNs to form a more complete and distinctive feature representation, and ensemble the predictions for robust decision-making. The proposed method was conducted on the publicly available LIDC-IDRI dataset in a 10-fold cross-validation experiment and it obtained an average accuracy of 93.25%, a sensitivity of 89.22%, a specificity of 95.82%, precision of 92.46%, F1 Score of 0.9114 and AUC of 0.9629. Experimental results illustrate that the RGD model achieves superior performance compared with the state-of-the-art methods. Moreover, the effectiveness of the fusion strategy has been confirmed by extensive ablation studies. In the future, the proposed model which performs well on the pulmonary nodule classification on CT images will be applied to increase confidence in the clinical diagnosis of lung cancer.

Pulmonary sclerosing pneumocytoma - approaching a solitary pulmonary nodule and the limitations of risk prediction models

Our case is an asymptomatic, non-smoking, East Asian woman in her 40s presenting with a solitary pulmonary nodule (SPN). On imaging, the 1.7 cm solid SPN located in the left upper lobe, was rounded in morphology and moderately fluorodeoxyglucose avid. The clinical pretest probability of malignancy assessed by risk prediction models such as Brock (19.1%), Mayo Clinic (56.2%) and Herder (51.4%) was discordant. She underwent a percutaneous CT-guided needle biopsy, establishing a diagnosis of pulmonary sclerosing pneumocytoma (PSP). PSP is a rare benign lung neoplasm with indolent growth characteristics that has been described predominantly in non-smoking women. Our case illustrates the limitations of applying existing risk prediction models in Asia where the epidemiology and biology of lung cancer differ significantly from the Caucasian derivation cohorts. Additionally, the risk models do not account for tuberculosis, which is endemic in Asia and can mimic malignancy. Non-surgical lung biopsy remains useful in minimising unnecessary thoracotomy.

Diagnostic Value of Artificial Intelligence-Assistant Diagnostic System Combined With Contrast-Enhanced Ultrasound in Thyroid TI-RADS 4 Nodules

OBJECTIVES

This study evaluated the diagnostic value of artificial intelligence-assistant diagnostic system combined with contrast-enhanced ultrasound in The American College of Radiology Thyroid Imaging, Reporting and Data System (ACR TI-RADS) 4 category thyroid nodules.

METHODS

Thyroid nodules that were evaluated as ACR TI-RADS 4 by conventional ultrasound were selected, all of which had pathological or fine needle aspiration (FNA) results. All nodules were examined by contrast-enhanced ultrasound (CEUS) and artificial intelligence (AI) analysis. The sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of AI, CEUS and their combined diagnosis were compared; Analyzed and compared the diagnostic efficiency of AI, CEUS and their combined diagnosis.

RESULTS

A total of 148 thyroid nodules were included in 140 patients, including 58 malignant nodules and 89 benign nodules. The sensitivity of combined diagnosis was significantly higher than that of AI or CEUS alone (P < .05). The NPV of AI, CEUS and combined diagnosis were statistically significant (P < .05). There was no significant difference in the diagnostic efficacy between AI and CEUS (P > .05), but there was a significant difference in NPV between AI and combined diagnosis (P < .05). The AUC of the combined diagnosis was 0.859, which was higher than that of AI, CEUS alone.

CONCLUSIONS

AI has a high diagnostic efficiency, which was helpful for radiologists to make rapid assessment. AI combined CEUS can significantly improve the diagnostic sensitivity and NPV, which was beneficial for the early detection of malignant nodules.

Artificial intelligence guided HRCT assessment predicts the severity of COVID-19 pneumonia based on clinical parameters

BACKGROUND

The purpose of the study was to compare the results of AI (artificial intelligence) analysis of the extent of pulmonary lesions on HRCT (high resolution computed tomography) images in COVID-19 pneumonia, with clinical data including laboratory markers of inflammation, to verify whether AI HRCT assessment can predict the clinical severity of COVID-19 pneumonia.

METHODS

The analyzed group consisted of 388 patients with COVID-19 pneumonia, with automatically analyzed HRCT parameters of volume: AIV (absolute inflammation), AGV (absolute ground glass), ACV (absolute consolidation), PIV (percentage inflammation), PGV (percentage ground glass), PCV (percentage consolidation). Clinical data included: age, sex, admission parameters: respiratory rate, oxygen saturation, CRP (C-reactive protein), IL6 (interleukin 6), IG - immature granulocytes, WBC (white blood count), neutrophil count, lymphocyte count, serum ferritin, LDH (lactate dehydrogenase), NIH (National Institute of Health) severity score; parameters of clinical course: in-hospital death, transfer to the ICU (intensive care unit), length of hospital stay.

RESULTS

The highest correlation coefficients were found for PGV, PIV, with LDH (respectively 0.65, 0.64); PIV, PGV, with oxygen saturation (respectively - 0.53, -0.52); AIV, AGV, with CRP (respectively 0.48, 0.46); AGV, AIV, with ferritin (respectively 0.46, 0.45). Patients with critical pneumonia had significantly lower oxygen saturation, and higher levels of immune-inflammatory biomarkers on admission. The radiological parameters of lung involvement proved to be strong predictors of transfer to the ICU (in particular, PGV ≥ cut-off point 29% with Odds Ratio (OR): 7.53) and in-hospital death (in particular: AIV ≥ cut-off point 831 cm³ with OR: 4.31).

CONCLUSIONS

Automatic analysis of HRCT images by AI may be a valuable method for predicting the severity of COVID-19 pneumonia. The radiological parameters of lung involvement correlate with laboratory markers of inflammation, and are strong predictors of transfer to the ICU and in-hospital death from COVID-19.

TRIAL REGISTRATION

National Center for Research and Development CRACoV-HHS project, contract number SZPITALE-JEDNOIMIENNE/18/2020.

Defining the road map to a UK national lung cancer screening programme

Lung cancer screening with low-dose CT was recommended by the UK National Screening Committee (UKNSC) in September, 2022, on the basis of data from trials showing a reduction in lung cancer mortality. These trials provide sufficient evidence to show clinical efficacy, but further work is needed to prove deliverability in preparation for a national roll-out of the first major targeted screening programme. The UK has been world leading in addressing logistical issues with lung cancer screening through clinical trials, implementation pilots, and the National Health Service (NHS) England Targeted Lung Health Check Programme. In this Policy Review, we describe the consensus reached by a multiprofessional group of experts in lung cancer screening on the key requirements and priorities for effective implementation of a programme. We summarise the output from a round-table meeting of clinicians, behavioural scientists, stakeholder organisations, and representatives from NHS England, the UKNSC, and the four UK nations. This Policy Review will be an important tool in the ongoing expansion and evolution of an already successful programme, and provides a summary of UK expert opinion for consideration by those organising and delivering lung cancer screenings in other countries.

The value of lung ultrasound in COVID-19 pneumonia, verified by high resolution computed tomography assessed by artificial intelligence

BACKGROUND

Lung ultrasound (LUS) is an increasingly popular imaging method in clinical practice. It became particularly important during the COVID-19 pandemic due to its mobility and ease of use compared to high-resolution computed tomography (HRCT). The objective of this study was to assess the value of LUS in quantifying the degree of lung involvement and in discrimination of lesion types in the course of COVID-19 pneumonia as compared to HRCT analyzed by the artificial intelligence (AI).

METHODS

This was a prospective observational study including adult patients hospitalized due to COVID-19 in whom initial HRCT and LUS were performed with an interval < 72 h. HRCT assessment was performed automatically by AI. We evaluated the correlations between the inflammation volume assessed both in LUS and HRCT, between LUS results and the HRCT structure of inflammation, and between LUS and the laboratory markers of inflammation. Additionally we compared the LUS results in subgroups depending on the respiratory failure throughout the hospitalization.

RESULTS

Study group comprised 65 patients, median 63 years old. For both lungs, the median LUS score was 19 (IQR-interquartile range 11-24) and the median CT score was 22 (IQR 16-26). Strong correlations were found between LUS and CT scores (for both lungs r = 0.75), and between LUS score and percentage inflammation volume (PIV) (r = 0.69). The correlations remained significant, if weakened, for individual lung lobes. The correlations between LUS score and the value of the percentage consolidation volume (PCV) divided by percentage ground glass volume (PGV), were weak or not significant. We found significant correlation between LUS score and C-reactive protein (r = 0.55), and between LUS score and interleukin 6 (r = 0.39). LUS score was significantly higher in subgroups with more severe respiratory failure.

CONCLUSIONS

LUS can be regarded as an accurate method to evaluate the extent of COVID-19 pneumonia and as a promising tool to estimate its clinical severity. Evaluation of LUS in the assessment of the structure of inflammation, requires further studies in the course of the disease.

TRIAL REGISTRATION

The study has been preregistered 13 Aug 2020 on clinicaltrials.gov with the number NCT04513210.

Comparison of single- and dual-energy CT combined with artificial intelligence for the diagnosis of pulmonary nodules

AIM

To explore the efficiency of single- and dual-energy computed tomography (CT) with artificial intelligence (AI) for the diagnosis of pulmonary nodules.

MATERIALS AND METHODS

In a prospective study, 682 patients undergoing a chest CT examination using a dual-energy system were divided randomly into two groups: single-energy mode (group S, n=341) and dual-energy mode (group D, n=341). CT images were first analysed automatically with the AI pulmonary nodule-detection software. CT features including nodule number, lesion size, and nodule type were then analysed by experienced radiologists to establish a reference diagnosis. Subsequently, the accuracy, sensitivity, false-positive rate, and miss rate of AI were calculated. Additionally, image quality and radiation dose were also compared between the two groups.

RESULTS

The contrast-to-noise ratio data suggested that the image quality of group D was superior to that of group S (0.16 ± 0.10 versus 0.00 ± 0.17), and the radiation dose of group D was lower than that of group S (0.32 ± 0.10 versus 0.62 ± 0.11 mSv.cm). Compared to group S, group D exhibited a significantly higher sensitivity and lower accuracy for nodule identification, size classification, and nodule type (all p<0.05, except for 5-10 mm and calcified nodules).

CONCLUSIONS

Compared with single-energy CT, dual-energy CT may significantly improve the sensitivity of AI for the diagnosis of pulmonary nodules and is practical for the screening of pulmonary nodules in a large population. In addition, dual-energy CT examination demonstrates improved image quality and is associated with reduced exposure to ionising radiation, but its accuracy is poorer.

Computed Tomography Imaging Features of Lung Cancer under Artificial Intelligence Algorithm and Its Correlation with Pathology

This study aims to investigate the relationship between the detection performance of an artificial intelligence (AI) algorithm and pathology in chest computed tomography (CT) images. In this study, a new pulmonary nodule (PN) detection algorithm was designed and developed on the three-dimensional (3D) connected domain algorithm. The appropriate grayscale threshold of CT images was selected, the CT images were converted into black-and-white images, and the useless images were removed. Then, the remaining lung images were formed into a 3D black-and-white pixel matrix. Labeling statistics was carried out, and the size, property, and location of PN could be measured and determined. A self-built database of PNs undergoing chest multislice spiral CT examination was retrospectively selected, and 150 cases were randomly selected by SPSS 22.0. Image processing was performed according to the algorithm and compared with the PN detected by radiologists; finally, the detection results were counted. There were 560 benign and malignant PNs, 312 malignant, and 248 benign. The algorithm detected 498 cases, of which 478 cases were detected accurately, and the sensitivity was 95.98%. The radiologist detected 424 cases, 364 cases were accurate, and the sensitivity was 85.85%. Compared with the detection results of radiologists, the algorithm detection results of nodules in solid nodules and ground glass nodules were more accurate. The detection results of nodules in the pleural connection type, peripheral type, central type, and hilar type were more accurate and statistically significant ( $P<0.05$ ). The malignancy, size, property, and location of different nodules could be accurately determined through CT images under this algorithm. It provided important support for the pathological research of lung cancer and prejudged the future development of PN in patients more accurately.

Radiomics and Artificial Intelligence Can Predict Malignancy of Solitary Pulmonary Nodules in the Elderly

Solitary pulmonary nodules (SPNs) are a diagnostic and therapeutic challenge for thoracic surgeons. Although such lesions are usually benign, the risk of malignancy remains significant, particularly in elderly patients, who represent a large segment of the affected population. Surgical treatment in this subset, which usually presents several comorbidities, requires careful evaluation, especially when pre-operative biopsy is not feasible and comorbidities may jeopardize the outcome. Radiomics and artificial intelligence (AI) are progressively being applied in predicting malignancy in suspicious nodules and assisting the decision-making process. In this study, we analyzed features of the radiomic images of 71 patients with SPN aged more than 75 years (median 79, IQR 76-81) who had undergone upfront pulmonary resection based on CT and PET-CT findings. Three different machine learning algorithms were applied-functional tree, Rep Tree and J48. Histology was malignant in 64.8% of nodules and the best predictive value was achieved by the J48 model (AUC 0.9). The use of AI analysis of radiomic features may be applied to the decision-making process in elderly frail patients with suspicious SPNs to minimize the false positive rate and reduce the incidence of unnecessary surgery.

Artificial intelligence: A critical review of applications for lung nodule and lung cancer

Artificial intelligence (AI) is a broad concept that usually refers to computer programs that can learn from data and perform certain specific tasks. In the recent years, the growth of deep learning, a successful technique for computer vision tasks that does not require explicit programming, coupled with the availability of large imaging databases fostered the development of multiple applications in the medical imaging field, especially for lung nodules and lung cancer, mostly through convolutional neural networks (CNN). Some of the first applications of AI is this field were dedicated to automated detection of lung nodules on X-ray and computed tomography (CT) examinations, with performances now reaching or exceeding those of radiologists. For lung nodule segmentation, CNN-based algorithms applied to CT images show excellent spatial overlap index with manual segmentation, even for irregular and ground glass nodules. A third application of AI is the classification of lung nodules between malignant and benign, which could limit the number of follow-up CT examinations for less suspicious lesions. Several algorithms have demonstrated excellent capabilities for the prediction of the malignancy risk when a nodule is discovered. These different applications of AI for lung nodules are particularly appealing in the context of lung cancer screening. In the field of lung cancer, AI tools applied to lung imaging have been investigated for distinct aims. First, they could play a role for the non-invasive characterization of tumors, especially for histological subtype and somatic mutation predictions, with a potential therapeutic impact. Additionally, they could help predict the patient prognosis, in combination to clinical data. Despite these encouraging perspectives, clinical implementation of AI tools is only beginning because of the lack of generalizability of published studies, of an inner obscure working and because of limited data about the impact of such tools on the radiologists' decision and on the patient outcome. Radiologists must be active participants in the process of evaluating AI tools, as such tools could support their daily work and offer them more time for high added value tasks.

Accuracy and efficiency of an artificial intelligence-based pulmonary broncho-vascular three-dimensional reconstruction system supporting thoracic surgery: retrospective and prospective validation study

BACKGROUND

Anthropomorphic phantoms are used in surgical planning and intervention. Ideal accuracy and high efficiency are prerequisites for its clinical application. We aimed to develop a fully automated artificial intelligence-based three-dimensional (3D) reconstruction system (AI system) to assist thoracic surgery and to determine its accuracy, efficiency, and safety for clinical use.

METHODS

This AI system was developed based on a 3D convolutional neural network (CNN) and optimized by gradient descent after training with 500 cases, achieving a Dice coefficient of 89.2%. Accuracy was verified by comparing virtual structures predicted by the AI system with anatomical structures of patients in retrospective (n = 113) and prospective cohorts (n = 139) who underwent lobectomy or segmentectomy at the Peking University Cancer Hospital. Operation time and blood loss were compared between the retrospective cohort (without AI assistance) and prospective cohort (with AI assistance) for safety evaluation. The time consumption for reconstruction and the quality score were compared between the AI system and manual reconstruction software (Mimics®) for efficiency validation. This study was registered at https://www.chictr.org.cn as ChiCTR2100050985.

FINDINGS

The AI system reconstructed 13,608 pulmonary segmental branches from retrospective and prospective cohorts, and 1573 branches of interest corresponding to phantoms were detectable during the operation for verification, achieving 100% and 97% accuracy for segmental bronchi, 97.2% and 99.1% for segmental arteries, and 93.2% and 98.8% for segmental veins, respectively. With the assistance of the AI system, the operation time was shortened by 24.5 min for lobectomy (p < 0.001) and 20 min for segmentectomy (p = 0.007). Compared to Mimics®, the AI system reduced the model reconstruction time by 14.2 min (p < 0.001), and it also outperformed Mimics® in model quality scores (p < 0.001).

INTERPRETATION

The AI system can accurately predict thoracic anatomical structures with higher efficiency than manual reconstruction software. Constant optimization and larger population validation are required.

FUNDING

This study was funded by the Beijing Natural Science Foundation (No. L222020) and other sources.

Integrative Serum Metabolic Fingerprints Based Multi-Modal Platforms for Lung Adenocarcinoma Early Detection and Pulmonary Nodule Classification

Identification of novel non-invasive biomarkers is critical for the early diagnosis of lung adenocarcinoma (LUAD), especially for the accurate classification of pulmonary nodule. Here, a multiplexed assay is developed on an optimized nanoparticle-based laser desorption/ionization mass spectrometry platform for the sensitive and selective detection of serum metabolic fingerprints (SMFs). Integrative SMFs based multi-modal platforms are constructed for the early detection of LUAD and the classification of pulmonary nodule. The dual modal model, metabolic fingerprints with protein tumor marker neural network (MP-NN), integrating SMFs with protein tumor marker carcinoembryonic antigen (CEA) via deep learning, shows superior performance compared with the single modal model Met-NN (p < 0.001). Based on MP-NN, the tri modal model MPI-RF integrating SMFs, tumor marker CEA, and image features via random forest demonstrates significantly higher performance than the clinical models (Mayo Clinic and Veterans Affairs) and the image artificial intelligence in pulmonary nodule classification (p < 0.001). The developed platforms would be promising tools for LUAD screening and pulmonary nodule management, paving the conceptual and practical foundation for the clinical application of omics tools.

Artificial Intelligence (AI) for Lung Nodules, From the AJR Special Series on AI Applications

Interest in artificial intelligence (AI) applications for lung nodules continues to grow among radiologists, particularly with the expanding eligibility criteria and clinical utilization of lung cancer screening CT. AI has been heavily investigated for detecting and characterizing lung nodules and for guiding prognostic assessment. AI tools have also been used for image postprocessing (e.g., rib suppression on radiography or vessel suppression on CT) and for noninterpretive aspects of reporting and workflow, including management of nodule follow-up. Despite growing interest in and rapid development of AI tools and FDA approval of AI tools for pulmonary nodule evaluation, integration into clinical practice has been limited. Challenges to clinical adoption have included concerns about generalizability, regulatory issues, technical hurdles in implementation, and human skepticism. Further validation of AI tools for clinical use and demonstration of benefit in terms of patient-oriented outcomes also are needed. This article provides an overview of potential applications of AI tools in the imaging evaluation of lung nodules and discusses the challenges faced by practices interested in clinical implementation of such tools.

Artificial intelligence and machine learning in cancer imaging

An increasing array of tools is being developed using artificial intelligence (AI) and machine learning (ML) for cancer imaging. The development of an optimal tool requires multidisciplinary engagement to ensure that the appropriate use case is met, as well as to undertake robust development and testing prior to its adoption into healthcare systems. This multidisciplinary review highlights key developments in the field. We discuss the challenges and opportunities of AI and ML in cancer imaging; considerations for the development of algorithms into tools that can be widely used and disseminated; and the development of the ecosystem needed to promote growth of AI and ML in cancer imaging.

Deep learning-based growth prediction for sub-solid pulmonary nodules on CT images

Background

Estimating the growth of pulmonary sub-solid nodules (SSNs) is crucial to the successful management of them during follow-up periods. The purpose of this study is to (1) investigate the measurement sensitivity of diameter, volume, and mass of SSNs for identifying growth and (2) seek to establish a deep learning-based model to predict the growth of SSNs.

Methods

A total of 2,523 patients underwent at least 2-year examination records retrospectively collected with sub-solid nodules. A total of 2,358 patients with 3,120 SSNs from the NLST dataset were randomly divided into training and validation sets. Patients from the Yibicom Health Management Center and Guangdong Provincial People’s Hospital were collected as an external test set (165 patients with 213 SSN). Trained models based on LUNA16 and Lndb19 datasets were employed to automatically obtain the diameter, volume, and mass of SSNs. Then, the increase rate in measurements between cancer and non-cancer groups was studied to evaluate the most appropriate way to identify growth-associated lung cancer. Further, according to the selected measurement, all SSNs were classified into two groups: growth and non-growth. Based on the data, the deep learning-based model (SiamModel) and radiomics model were developed and verified.

Results

The double time of diameter, volume, and mass were 711 vs. 963 days (P = 0.20), 552 vs. 621 days (P = 0.04) and 488 vs. 623 days (P< 0.001) in the cancer and non-cancer groups, respectively. Our proposed SiamModel performed better than the radiomics model in both the NLST validation set and external test set, with an AUC of 0.858 (95% CI 0.786–0.921) and 0.760 (95% CI 0.646–0.857) in the validation set and 0.862 (95% CI 0.789–0.927) and 0.681 (95% CI 0.506–0.841) in the external test set, respectively. Furthermore, our SiamModel could use the data from first-time CT to predict the growth of SSNs, with an AUC of 0.855 (95% CI 0.793–0.908) in the NLST validation set and 0.821 (95% CI 0.725–0.904) in the external test set.

Conclusion

Mass increase rate can reflect more sensitively the growth of SSNs associated with lung cancer than diameter and volume increase rates. A deep learning-based model has a great potential to predict the growth of SSNs.

[Low-dose Spiral Computed Tomography in Lung Cancer Screening]

Lung cancer is one of the malignant tumors with the highest morbidity and mortality in the world. The low early diagnosis rate and poor prognosis of patients have caused serious social burden. Regular screening of high-risk population by low-dose spiral computed tomography (LDCT) can significantly improve the early diagnosis rate of lung cancer and bring new opportunities for the diagnosis and treatment of lung cancer. In recent years, LDCT lung cancer screening programs have been carried out in many countries around the world and achieved good results, but there are still some controversies in the selection of screening subjects, screening frequency, cost effectiveness and other aspects. In this paper, the key factors of LDCT lung cancer screening, screening effect, pulmonary nodule management and artificial intelligence contribution to the development of LDCT will be reviewed, and the application progress of LDCT in lung cancer screening will be discussed.
.

Artificial Intelligence Tool for Assessment of Indeterminate Pulmonary Nodules Detected with CT

Background Limited data are available regarding whether computer-aided diagnosis (CAD) improves assessment of malignancy risk in indeterminate pulmonary nodules (IPNs). Purpose To evaluate the effect of an artificial intelligence-based CAD tool on clinician IPN diagnostic performance and agreement for both malignancy risk categories and management recommendations. Materials and Methods This was a retrospective multireader multicase study performed in June and July 2020 on chest CT studies of IPNs. Readers used only CT imaging data and provided an estimate of malignancy risk and a management recommendation for each case without and with CAD. The effect of CAD on average reader diagnostic performance was assessed using the Obuchowski-Rockette and Dorfman-Berbaum-Metz method to calculate estimates of area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Multirater Fleiss κ statistics were used to measure interobserver agreement for malignancy risk and management recommendations. Results A total of 300 chest CT scans of IPNs with maximal diameters of 5-30 mm (50.0% malignant) were reviewed by 12 readers (six radiologists, six pulmonologists) (patient median age, 65 years; IQR, 59-71 years; 164 [55%] men). Readers' average AUC improved from 0.82 to 0.89 with CAD (P < .001). At malignancy risk thresholds of 5% and 65%, use of CAD improved average sensitivity from 94.1% to 97.9% (P = .01) and from 52.6% to 63.1% (P < .001), respectively. Average reader specificity improved from 37.4% to 42.3% (P = .03) and from 87.3% to 89.9% (P = .05), respectively. Reader interobserver agreement improved with CAD for both the less than 5% (Fleiss κ, 0.50 vs 0.71; P < .001) and more than 65% (Fleiss κ, 0.54 vs 0.71; P < .001) malignancy risk categories. Overall reader interobserver agreement for management recommendation categories (no action, CT surveillance, diagnostic procedure) also improved with CAD (Fleiss κ, 0.44 vs 0.52; P = .001). Conclusion Use of computer-aided diagnosis improved estimation of indeterminate pulmonary nodule malignancy risk on chest CT scans and improved interobserver agreement for both risk stratification and management recommendations. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Yanagawa in this issue.

Innovations in thoracic imaging: CT, radiomics, AI and x-ray velocimetry

In recent years, pulmonary imaging has seen enormous progress, with the introduction, validation and implementation of new hardware and software. There is a general trend from mere visual evaluation of radiological images to quantification of abnormalities and biomarkers, and assessment of ‘non visual’ markers that contribute to establishing diagnosis or prognosis. Important catalysts to these developments in thoracic imaging include new indications (like computed tomography [CT] lung cancer screening) and the COVID‐19 pandemic. This review focuses on developments in CT, radiomics, artificial intelligence (AI) and x‐ray velocimetry for imaging of the lungs. Recent developments in CT include the potential for ultra‐low‐dose CT imaging for lung nodules, and the advent of a new generation of CT systems based on photon‐counting detector technology. Radiomics has demonstrated potential towards predictive and prognostic tasks particularly in lung cancer, previously not achievable by visual inspection by radiologists, exploiting high dimensional patterns (mostly texture related) on medical imaging data. Deep learning technology has revolutionized the field of AI and as a result, performance of AI algorithms is approaching human performance for an increasing number of specific tasks. X‐ray velocimetry integrates x‐ray (fluoroscopic) imaging with unique image processing to produce quantitative four dimensional measurement of lung tissue motion, and accurate calculations of lung ventilation.

See relatedEditorial

Differential diagnosis of thyroid nodules by the Demetics ultrasound-assisted diagnosis system and contrast-enhanced ultrasound combined with thyroid image reporting and data systems

BACKGROUND

More and more new ultrasound techniques with their own characteristics are applied in the differential diagnosis of thyroid nodules. This study amied to assess and compare the diagnostic value of the Demetics ultrasound-assisted diagnosis system and contrast-enhanced ultrasound (CEUS) combined with the Thyroid Image Reporting and Data Systems (TI-RADS) for thyroid nodules.

DESIGN AND PATIENTS

A total of 600 thyroid nodules with pathological findings were retrospectively analysed. Demetics and CEUS were performed for all nodules. The diagnostic efficacy of Demetics and CEUS for nodules of different sizes was evaluated and compared in terms of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (LR+) and negative likelihood ratio (LR-). The characteristics of nodules diagnosed and misdiagnosed by Demetics were compared to analyse the factors affecting the diagnostic accuracy of Demetics. The necessity of CEUS for nodules that are prone to misdiagnosis in Demetics was assessed.

RESULTS

Both Demetics and CEUS can be used for the differential diagnosis of benign and malignant thyroid nodules of different sizes. The diagnostic agreement between Demetics and CEUS for thyroid nodules of different sizes was moderate, substantial and fair, respectively. The sensitivity and NPV of Demetics were higher than those of CEUS, and the specificity, PPV and LR+ of CEUS were higher than that of Demetics. The LR- of Demetics was lower than those of CEUS. There were significant differences in age, calcification and margin in analysing the factors affecting Demetics. CEUS correctly diagnosed 50 of the 101 nodules misdiagnosed by Demetics.

CONCLUSIONS

Demetics showed high sensitivity in diagnosing thyroid nodules, while CEUS showed high specificity. In clinical practice, CEUS can further improve the diagnostic accuracy for nodules that are easily misdiagnosed by Demetics.

Low-dose computed tomography lung cancer screening: Clinical evidence and implementation research

Lung cancer causes more deaths than breast, cervical, and colorectal cancer combined. Nevertheless, population-based lung cancer screening is still not considered standard practice in most countries worldwide. Early lung cancer detection leads to better survival outcomes: patients diagnosed with stage 1A lung cancer have a >75% 5-year survival rate, compared to <5% at stage 4. Low-dose computed tomography (LDCT) thorax imaging for the secondary prevention of lung cancer has been studied at length, and has been shown to significantly reduce lung cancer mortality in high-risk populations. The US National Lung Screening Trial reported a 20% overall reduction in lung cancer mortality when comparing LDCT to chest X-ray, and the Nederlands-Leuvens Longkanker Screenings Onderzoek (NELSON) trial more recently reported a 24% reduction when comparing LDCT to no screening. Hence, the focus has now shifted to implementation research. Consequently, the 4-IN-THE-LUNG-RUN consortium based in five European countries, has set up a large-scale multicenter implementation trial. Successful implementation of and accessibility to LDCT lung cancer screening are dependent on many factors, not limited to population selection, recruitment strategy, computed tomography screening frequency, lung-nodule management, participant compliance, and cost effectiveness. This review provides an overview of current evidence for LDCT lung cancer screening, and draws attention to major factors that need to be addressed to successfully implement standardized, effective, and accessible screening throughout Europe. Evidence shows that through the appropriate use of risk-prediction models and a more personalized approach to screening, efficacy could be improved. Furthermore, extending the screening interval for low-risk individuals to reduce costs and associated harms is a possibility, and through the use of volumetric-based measurement and follow-up, false positive results can be greatly reduced. Finally, smoking cessation programs could be a valuable addition to screening programs and artificial intelligence could offer a solution to the added workload pressures radiologists are facing.

Computed tomography-based radiomics for identifying pulmonary cryptococcosis mimicking lung cancer

BACKGROUND

Pulmonary cryptococcosis (PC) is an invasive pulmonary fungal disease, and nodule/mass-type PC may mimic lung cancer (LC) in imaging appearance. Thus, an accurate diagnosis of nodule/mass-type PC is beneficial for appropriate management. However, the differentiation of nodule/mass-type PC from LC through computed tomography (CT) is still challenging.

PURPOSE

To develop and externally test a CT-based radiomics model for differentiating nodule/mass-type PC from LC.

METHODS

In this retrospective study, patients with nodule/mass-type PC or LC who underwent non-enhanced chest CT were included: institution 1 was for the training set, and institutions 2 and 3 were for the external test set. Large quantities of radiomics features were extracted. The radiomics score (Rad-score) was calculated using the linear discriminant analysis, and a subsequent 5-fold cross-validation was performed. A combined model was developed by incorporating Rad-score and clinical factors. Finally, the models were tested with an external test set and compared using the area under the receiver operating characteristic curve (AUC).

RESULTS

A total of 168 patients (45 with PC and 123 with LC) were in the training set, and 72 (36 with PC and 36 with LC) were in the external test set. Of the 81 patients with PC, 30 were immunocompromised (37%). Rad-score, comprised of 18 features, had an AUC of 0.844 after 5-fold cross-validation, which was lower than that (AUC = 0.943, P = 0.003) of the combined model integrating Rad-score, age, lobulation, pleural retraction, and patches. In the external test set, Rad-score and the combined model obtained good predictive performance (AUC = 0.824 for Rad-score, and 0.869 for the combined model). Moreover, the combined model outperformed the clinical model in the cross-validation and external test (0.943 vs. 0.810, P <0.001; 0.869 vs. 0.769, P = 0.011).

CONCLUSIONS

The proposed combined model exhibits a good differential diagnostic performance between nodule/mass-type PC and LC. The CT-based radiomics analysis has the potential to serve as an effective tool for the differentiation of nodule/mass-type PC from LC in clinical practice. This article is protected by copyright. All rights reserved.

[Chinese Experts Consensus on Artificial Intelligence Assisted Management for Pulmonary Nodule (2022 Version)]

Low-dose computed tomography (CT) for lung cancer screening has been proven to reduce lung cancer deaths in the screening group compared with the control group. The increasing number of pulmonary nodules being detected by CT scans significantly increase the workload of the radiologists for scan interpretation. Artificial intelligence (AI) has the potential to increase the efficiency of pulmonary nodule discrimination and has been tested in preliminary studies for nodule management. As more and more artificial AI products are commercialized, the consensus statement has been organized in a collaborative effort by Thoracic Surgery Committee, Department of Simulated Medicine, Wu Jieping Medical Foundation to aid clinicians in the application of AI-assisted management for pulmonary nodules.
.

How AI Can Help in the Diagnostic Dilemma of Pulmonary Nodules

Simple Summary

Pulmonary nodules are considered a sign of bronchogenic carcinoma, detecting them early will reduce their progression and can save lives. Lung cancer is the second most common type of cancer in both men and women. This manuscript discusses the current applications of artificial intelligence (AI) in lung segmentation as well as pulmonary nodule segmentation and classification using computed tomography (CT) scans, published in the last two decades, in addition to the limitations and future prospects in the field of AI.

Abstract

Pulmonary nodules are the precursors of bronchogenic carcinoma, its early detection facilitates early treatment which save a lot of lives. Unfortunately, pulmonary nodule detection and classification are liable to subjective variations with high rate of missing small cancerous lesions which opens the way for implementation of artificial intelligence (AI) and computer aided diagnosis (CAD) systems. The field of deep learning and neural networks is expanding every day with new models designed to overcome diagnostic problems and provide more applicable and simply used models. We aim in this review to briefly discuss the current applications of AI in lung segmentation, pulmonary nodule detection and classification.

Artificial Intelligence-Aided Diagnosis Software to Identify Highly Suspicious Pulmonary Nodules

Introduction

To evaluate the value of artificial intelligence (AI)-assisted software in the diagnosis of lung nodules using a combination of low-dose computed tomography (LDCT) and high-resolution computed tomography (HRCT).

Method

A total of 113 patients with pulmonary nodules were screened using LDCT. For nodules with the largest diameters, an HRCT local-target scanning program (combined scanning scheme) and a conventional-dose CT scanning scheme were also performed. Lung nodules were subjectively assessed for image signs and compared by size and malignancy rate measured by AI-assisted software. The nodules were divided into improved visibility and identical visibility groups based on differences in the number of signs identified through the two schemes.

Results

The nodule volume and malignancy probability for subsolid nodules significantly differed between the improved and identical visibility groups. For the combined scanning protocol, we observed significant between-group differences in subsolid nodule malignancy rates.

Conclusion

Under the operation and decision of AI, the combined scanning scheme may be beneficial for screening high-risk populations.

Outstanding negative prediction performance of solid pulmonary nodule volume AI for ultra-LDCT baseline lung cancer screening risk stratification

OBJECTIVE

To evaluate performance of AI as a standalone reader in ultra-low-dose CT lung cancer baseline screening, and compare it to that of experienced radiologists.

METHODS

283 participants who underwent a baseline ultra-LDCT scan in Moscow Lung Cancer Screening, between February 2017-2018, and had at least one solid lung nodule, were included. Volumetric nodule measurements were performed by five experienced blinded radiologists, and independently assessed using an AI lung cancer screening prototype (AVIEW LCS, v1.0.34, Coreline Soft, Co. ltd, Seoul, Korea) to automatically detect, measure, and classify solid nodules. Discrepancies were stratified into two groups: positive-misclassification (PM); nodule classified by the reader as a NELSON-plus /EUPS-indeterminate/positive nodule, which at the reference consensus read was < 100 mm3, and negative-misclassification (NM); nodule classified as a NELSON-plus /EUPS-negative nodule, which at consensus read was ≥ 100 mm3.

RESULTS

1149 nodules with a solid-component were detected, of which 878 were classified as solid nodules. For the largest solid nodule per participant (n = 283); 61 [21.6 %; 53 PM, 8 NM] discrepancies were reported for AI as a standalone reader, compared to 43 [15.1 %; 22 PM, 21 NM], 36 [12.7 %; 25 PM, 11 NM], 29 [10.2 %; 25 PM, 4 NM], 28 [9.9 %; 6 PM, 22 NM], and 50 [17.7 %; 15 PM, 35 NM] discrepancies for readers 1, 2, 3, 4, and 5 respectively.

CONCLUSION

Our results suggest that through the use of AI as an impartial reader in baseline lung cancer screening, negative-misclassification results could exceed that of four out of five experienced radiologists, and radiologists' workload could be drastically diminished by up to 86.7%.

Artificial intelligence in thoracic surgery: a narrative review

Objective

The aim of this article is to review the current applications of artificial intelligence in thoracic surgery, from diagnosis and pulmonary disease management, to preoperative risk-assessment, surgical planning, and outcomes prediction.

Background

Artificial intelligence implementation in healthcare settings is rapidly growing, though its widespread use in clinical practice is still limited. The employment of machine learning algorithms in thoracic surgery is wide-ranging, including all steps of the clinical pathway.

Methods

We performed a narrative review of the literature on Scopus, PubMed and Cochrane databases, including all the relevant studies published in the last ten years, until March 2021.

Conclusion

Machine learning methods are promising encouraging results throughout the key issues of thoracic surgery, both clinical, organizational, and educational. Artificial intelligence-based technologies showed remarkable efficacy to improve the perioperative evaluation of the patient, to assist the decision-making process, to enhance the surgical performance, and to optimize the operating room scheduling. Still, some concern remains about data supply, protection, and transparency, thus further studies and specific consensus guidelines are needed to validate these technologies for daily common practice.

Keywords

Artificial intelligence (AI); thoracic surgery; machine learning; lung resection; perioperative medicine

Epipericardial Fat Necrosis: A Retrospective Analysis in Japan

Objective Epipericardial fat necrosis (EFN) has been considered to be a rare cause of acute chest pain, and especially important for emergency physicians. Chest computed tomography (CT) is often used for the diagnosis of EFN after excluding life-threatening states, such as acute coronary syndrome and pulmonary embolism. While the proportion of EFN patients who underwent chest CT in emergency departments is being clarified, little is still known about other departments in Japan. To investigate the proportion of EFN patients who underwent chest CT for acute chest pain in various departments. Methods Chest CT performed from January 2015 to July 2020 in Asahikawa Medical University Hospital in Japan was retrospectively analyzed in this study. All images were reviewed by two radiologists. Results There were 373 outpatients identified by a search using the word 'chest pain' who underwent chest CT. Eight patients satisfying the imaging criteria were diagnosed with EFN. The proportions of patients diagnosed with EFN were 10.7%, 4.8%, 2.8%, 0.9% and 0% in the departments of general medicine, cardiovascular surgery, emergency medicine, cardiovascular internal medicine and respiratory medicine, respectively. Only 12.5% of the patients were correctly diagnosed with EFN, and the other patients were treated for musculoskeletal symptoms, acute pericarditis or hypochondriasis. Conclusion EFN is not rare and is often overlooked in various departments. All physicians as well as emergency physicians should consider the possibility of EFN as the cause of pleuritic chest pain.

Integration of Artificial Intelligence, Blockchain, and Wearable Technology for Chronic Disease Management: A New Paradigm in Smart Healthcare

Chronic diseases are a growing concern worldwide, with nearly 25% of adults suffering from one or more chronic health conditions, thus placing a heavy burden on individuals, families, and healthcare systems. With the advent of the "Smart Healthcare" era, a series of cutting-edge technologies has brought new experiences to the management of chronic diseases. Among them, smart wearable technology not only helps people pursue a healthier lifestyle but also provides a continuous flow of healthcare data for disease diagnosis and treatment by actively recording physiological parameters and tracking the metabolic state. However, how to organize and analyze the data to achieve the ultimate goal of improving chronic disease management, in terms of quality of life, patient outcomes, and privacy protection, is an urgent issue that needs to be addressed. Artificial intelligence (AI) can provide intelligent suggestions by analyzing a patient's physiological data from wearable devices for the diagnosis and treatment of diseases. In addition, blockchain can improve healthcare services by authorizing decentralized data sharing, protecting the privacy of users, providing data empowerment, and ensuring the reliability of data management. Integrating AI, blockchain, and wearable technology could optimize the existing chronic disease management models, with a shift from a hospital-centered model to a patient-centered one. In this paper, we conceptually demonstrate a patient-centric technical framework based on AI, blockchain, and wearable technology and further explore the application of these integrated technologies in chronic disease management. Finally, the shortcomings of this new paradigm and future research directions are also discussed.

Convolutional Neural Network-Based Diagnostic Model for a Solid, Indeterminate Solitary Pulmonary Nodule or Mass on Computed Tomography

PURPOSE

To establish a non-invasive diagnostic model based on convolutional neural networks (CNNs) to distinguish benign from malignant lesions manifesting as a solid, indeterminate solitary pulmonary nodule (SPN) or mass (SPM) on computed tomography (CT).

METHOD

A total of 459 patients with solid indeterminate SPNs/SPMs on CT were ultimately included in this retrospective study and assigned to the train (n=366), validation (n=46), and test (n=47) sets. Histopathologic analysis was available for each patient. An end-to-end CNN model was proposed to predict the natural history of solid indeterminate SPN/SPMs on CT. Receiver operating characteristic curves were plotted to evaluate the predictive performance of the proposed CNN model. The accuracy, sensitivity, and specificity of diagnoses by radiologists alone were compared with those of diagnoses by radiologists by using the CNN model to assess its clinical utility.

RESULTS

For the CNN model, the AUC was 91% (95% confidence interval [CI]: 0.83-0.99) in the test set. The diagnostic accuracy of radiologists with the CNN model was significantly higher than that without the model (89 vs. 66%, P<0.01; 87 vs. 61%, P<0.01; 85 vs. 66%, P=0.03, in the train, validation, and test sets, respectively). In addition, while there was a slight increase in sensitivity, the specificity improved significantly by an average of 42% (the corresponding improvements in the three sets ranged from 43, 33, and 42% to 82, 78, and 84%, respectively; P<0.01 for all).

CONCLUSION

The CNN model could be a valuable tool in non-invasively differentiating benign from malignant lesions manifesting as solid, indeterminate SPNs/SPMs on CT.

Diagnostic Value of Deep Learning-Based CT Feature for Severe Pulmonary Infection

The study aimed to explore the diagnostic value of computed tomography (CT) images based on cavity convolution U-Net algorithm for patients with severe pulmonary infection. A new lung CT image segmentation algorithm (U-Net+ deep convolution (DC)) was proposed based on U-Net network and compared with convolutional neural network (CNN) algorithm. Then, it was applied to CT image diagnosis of 100 patients with severe lung infection in The Second Affiliated Hospital of Fujian Medical University hospital and compared with traditional methods, and its sensitivity, specificity, and accuracy were compared. It was found that the single training time and loss of U-Net + DC algorithm were reduced by 59.4% and 9.8%, respectively, compared with CNN algorithm, while Dice increased by 3.6%. The lung contour segmented by the proposed model was smooth, which was the closest to the gold standard. Fungal infection, bacterial infection, viral infection, tuberculosis infection, and mixed infection accounted for 28%, 18%, 7%, 7%, and 40%, respectively. 36%, 38%, 26%, 17%, and 20% of the patients had ground-glass shadow, solid shadow, nodule or mass shadow, reticular or linear shadow, and hollow shadow in CT, respectively. The incidence of various CT characteristics in patients with fungal and bacterial infections was statistically significant (P < 0.05). The specificity (94.32%) and accuracy (97.22%) of CT image diagnosis based on U-Net + DC algorithm were significantly higher than traditional diagnostic method (75.74% and 74.23%), and the differences were statistically significant (P < 0.05). The network of the algorithm in this study demonstrated excellent image segmentation effect. The CT image based on the U-Net + DC algorithm can be used for the diagnosis of patients with severe pulmonary infection, with high diagnostic value.

The Prevalence of Benign Pathology Following Major Pulmonary Resection for Suspected Malignancy

BACKGROUND

In the era of lung cancer screening with low-dose computed tomography, there is concern that high false-positive rates may lead to an increase in nontherapeutic lung resection. The aim of this study is to determine the current rate of major pulmonary resection for ultimately benign pathology.

MATERIALS AND METHODS

A single-institution, retrospective analysis of all patients > 18 y who underwent major pulmonary resection between 2013 and 2018 for suspected malignancy and had benign final pathology was performed.

RESULTS

Of 394 major pulmonary resections performed for known or presumed malignancy, 10 (2.5%) were benign. Of these 10, the mean age was 61.1 y (SD 14.6). Most were current or former smokers (60%). Ninety percent underwent a fluorodeoxyglucose positron emission tomography scan. Median nodule size was 27 mm (IQR 21-35) and most were in the right middle lobe (50%). Preoperative biopsy was performed in four (40%) but were nondiagnostic. Video-assisted thoracoscopic lobectomy (70%) was the most common surgical approach. Final pathology revealed three (30%) infectious, three (30%) inflammatory, two (20%) fibrotic, and two (20%) benign neoplastic nodules. Two (20%) patients had perioperative complications, both of which were prolonged air leaks, one (10%) patient was readmitted within 30 d, and there was no mortality.

CONCLUSIONS

A small percentage of patients (2.5% in our series) may undergo major pulmonary resection for unexpectedly benign pathology. Knowledge of this rate is useful to inform shared decision-making models between surgeons and patients and evaluation of thoracic surgery program performance.

Computed Tomography Image under Convolutional Neural Network Deep Learning Algorithm in Pulmonary Nodule Detection and Lung Function Examination

The objective of this study was to perform segmentation and extraction of CT images of pulmonary nodules based on convolutional neural networks (CNNs). The Mask-RCNN algorithm model is a typical end-to-end image segmentation model, which uses the R-FCN structure for nodule detection. The effect of applying the two algorithm models to the computed tomography (CT) diagnosis of pulmonary nodules was analyzed, and different indexes of pulmonary nodule CT images in lung function examination after algorithm optimization were compared. A total of 56 patients diagnosed with pulmonary nodules by surgery or puncture were taken as the research objects. Based on the Mask-RCNN algorithm, a model for CT image segmentation processing of pulmonary nodules was proposed. Subsequently, the 3D Faster-RCNN model was used to label the nodules in the pulmonary nodules. The experimental results showed that the trained Mask-RCNN algorithm model can effectively complete the segmentation task of lung CT images, but there was a little jitter at the boundary. The speed of R-FCN algorithm for nodular detection was 0.172 seconds/picture, and the accuracy was 88.9%. CT scans were performed on the 56 patients based on a deep learning algorithm. The results showed that 30 cases of malignant pulmonary nodules were confirmed, and the diagnostic accuracy was 93.75%. There were 22 benign lesions, the diagnostic accuracy was 91.67%, and the overall diagnostic accuracy was 92.85%. This study effectively improved the diagnostic efficiency of CT images of pulmonary nodules, and the accuracy of CT images in the diagnosis of pulmonary nodules was analyzed and evaluated. It provided theoretical support for the follow-up diagnosis of pulmonary nodules and the treatment of lung cancer. It also significantly improved the diagnostic effect and detection efficiency of pulmonary nodules.

Consecutive Serial Non-Contrast CT Scan-Based Deep Learning Model Facilitates the Prediction of Tumor Invasiveness of Ground-Glass Nodules

Introduction

Tumors are continuously evolving biological systems which can be monitored by medical imaging. Previous studies only focus on single timepoint images, whether the performance could be further improved by using serial noncontrast CT imaging obtained during nodule follow-up management remains unclear. In this study, we evaluated DL model for predicting tumor invasiveness of GGNs through analyzing time series CT images.

Methods

A total of 168 pathologically confirmed GGN cases (48 noninvasive lesions and 120 invasive lesions) were retrospectively collected and randomly assigned to the development dataset (n = 123) and independent testing dataset (n = 45). All patients underwent consecutive noncontrast CT examinations, and the baseline CT and 3-month follow-up CT images were collected. The gross region of interest (ROI) patches containing only tumor region and the full ROI patches including both tumor and peritumor regions were cropped from CT images. A baseline model was built on the image features and demographic features. Four DL models were proposed: two single-DL model using gross ROI (model 1) or full ROI patches (model 3) from baseline CT images, and two serial-DL models using gross ROI (model 2) or full ROI patches (model 4) from consecutive CT images (baseline scan and 3-month follow-up scan). In addition, a combined model integrating serial full ROI patches and clinical information was also constructed. The performance of these predictive models was assessed with respect to discrimination and clinical usefulness.

Results

The area under the curve (AUC) of the baseline model, models 1, 2, 3, and 4 were 0.562 [(95% confidence interval (C)], 0.406~0.710), 0.693 (95% CI, 0.538-0.822), 0.787 (95% CI, 0.639-0.895), 0.727 (95% CI, 0.573-0.849), and 0.811 (95% CI, 0.667-0.912) in the independent testing dataset, respectively. The results indicated that the peritumor region had potential to contribute to tumor invasiveness prediction, and the model performance was further improved by integrating imaging scans at multiple timepoints. Furthermore, the combined model showed best discrimination ability, with AUC, sensitivity, specificity, and accuracy achieving 0.831 (95% CI, 0.690-0.926), 86.7%, 73.3%, and 82.2%, respectively.

Conclusion

The DL model integrating full ROIs from serial CT images shows improved predictive performance in differentiating noninvasive from invasive GGNs than the model using only baseline CT images, which could benefit the clinical management of GGNs.

Dosing Schedules of Gemcitabine and nab-Paclitaxel for Older Adults With Metastatic Pancreatic Cancer

Background

Gemcitabine and nab-paclitaxel (GA) is a first-line treatment for patients with metastatic pancreatic cancer (mPDAC). The traditional dosing schedule of GA is days 1, 8, and 15 of a 28-day cycle. Frequently, older adults are given a modified dosing schedule using 2 doses per cycle because of toxicity. We retrospectively analyzed treatment patterns and outcomes of older adults with mPDAC given these 2 dosing schedules.

Methods

Patients 65 years or older with mPDAC treated with GA in a nationwide real-world database between January 1, 2014, and May 31, 2019, were included. Demographic, disease, and treatment information were collected. Patients were grouped by dosing at treatment initiation (traditional vs modified dosing schedules). Endpoints were time on treatment (TOT) and overall survival (OS) in patients receiving at least 2 cycles. All statistical tests were 2-sided.

Results

1317 patients were included (traditional dosing schedule: n = 842; modified dosing schedule: n = 475). Median age at diagnosis was 72 and 73 years for traditional and modified dosing schedules, respectively (P < .001), but sex, race, and performance status were not statistically significantly different. The median TOT and OS were better for the traditional vs modified dosing schedule (unadjusted median TOT, first-line = 4.18 vs 3.26 mo, P =.04; OS = 9.44 vs 7.63 mo, P =.003).

Conclusion

In this real-world cohort, treatment of older mPDAC patients with a modified dosing schedule of GA resulted in shorter TOT and worse OS vs a traditional dosing schedule. With the caveats of potential confounding that exist in a nonrandomized retrospective database, these results suggest that dose intensity may be important, and prospective studies are necessary to ensure we treat our patients most effectively.

A systematic review and meta-analysis of diagnostic performance and physicians' perceptions of artificial intelligence (AI)-assisted CT diagnostic technology for the classification of pulmonary nodules

Background

Lung cancer was the second most commonly diagnosed cancer and the leading cause of cancer death in 2020. Although artificial intelligence (AI)-assisted diagnostic technologies have shown promise and has been used in clinical practice in recent years, no products related to AI-assisted CT diagnostic technologies for the classification of pulmonary nodules have been approved by the National Medical Products Administration in China. The objective of this article was to systematically review the diagnostic performance of AI-assisted CT diagnostic technology for the classification of pulmonary nodules as benign or malignant and to analyze physicians’ perceptions of this technology in China.

Methods

All relevant studies from 6 literature databases were searched and screened according to the inclusion and exclusion criteria. Data were extracted and the study quality was assessed by two reviewers. The study heterogeneity and publication bias were estimated. A questionnaire survey on the perceptions of physicians was conducted in 9 public tertiary hospitals in China. A meta-analysis, meta-regression and univariate logistic model were used in the systematic review and to explore the association of physicians’ perceptions with their rate of support for the clinical application of the technology.

Results

Twenty-seven studies with 5,727 pulmonary nodules were finally included in the meta-analysis. We found that the quality of the included studies was generally acceptable and that the pooled sensitivity and specificity of AI-assisted CT diagnostic technology for the classification of pulmonary nodules as benign or malignant were 0.90 and 0.89, respectively. The pooled diagnostic odds ratio (DOR) was 70.33. The majority of the surveyed physicians in China perceived “reduced workload for radiologists” and “improved diagnostic efficiency” as the important benefits of this technology. In addition, diagnostic accuracy (including misdiagnosis) and practical experience were significantly associated with whether physicians supported its clinical application.

Conclusions

In the context of lung cancer diagnosis, AI-assisted CT diagnostic technology for the classification of pulmonary nodules as benign or malignant has good diagnostic performance, but its specificity needs to be improved.

Clinical evaluation of a deep-learning-based computer-aided detection system for the detection of pulmonary nodules in a large teaching hospital

AIM

To evaluate a deep-learning-based computer-aided detection (DL-CAD) software system for pulmonary nodule detection on computed tomography (CT) images and assess its added value in the clinical practice of a large teaching hospital.

MATERIALS AND METHODS

A retrospective analysis was performed of 145 chest CT examinations by comparing the output of the DL-CAD software with a reference standard based on the consensus reading of three radiologists. For every nodule in each scan, the location, composition, and maximum diameter in the axial plane were recorded. The subgroup of chest CT examinations (n = 97) without any nodules was used to determine the negative predictive value at the given clinical sensitivity threshold setting.

RESULTS

The radiologists found 91 nodules and the CAD system 130 nodules of which 80 were true positive. The measured sensitivity was 88% and the mean false-positive rate was 1.04 false positives/scan. The negative predictive value was 95%. For 23 nodules, there was a size discrepancy of which 19 (83%) were measured smaller by the radiologist. The agreement of nodule composition between the CAD results and the reference standard was 95%.

CONCLUSIONS

The present study found a sensitivity of 88% and a false-positive rate of 1.04 false positives/scan, which match the vendor specification. Together with the measured negative predictive value of 95% the system performs very well; however, these rates are still not good enough to replace the radiologist, even for the specific task of nodule detection. Furthermore, a surprisingly high rate of overestimation of nodule size was observed, which can lead to too many follow-up examinations.

Predicting Tyrosine Kinase Inhibitor Treatment Response in Stage IV Lung Adenocarcinoma Patients With EGFR Mutation Using Model-Based Deep Transfer Learning

Background

For stage IV patients harboring EGFR mutations, there is a differential response to the first-line TKI treatment. We constructed three-dimensional convolutional neural networks (CNN) with deep transfer learning to stratify patients into subgroups with different response and progression risks.

Materials and Methods

From 2013 to 2017, 339 patients with EGFR mutation receiving first-line TKI treatment were included. Progression-free survival (PFS) time and progression patterns were confirmed by routine follow-up and restaging examinations. Patients were divided into two subgroups according to the median PFS (<=9 months, > 9 months). We developed a PFS prediction model and a progression pattern classification model using transfer learning from a pre-trained EGFR mutation classification 3D CNN. Clinical features were fused with the 3D CNN to build the final hybrid prediction model. The performance was quantified using area under receiver operating characteristic curve (AUC), and model performance was compared by AUCs with Delong test.

Results

The PFS prediction CNN showed an AUC of 0.744 (95% CI, 0.645–0.843) in the independent validation set and the hybrid model of CNNs and clinical features showed an AUC of 0.771 (95% CI, 0.676–0.866), which are significantly better than clinical features-based model (AUC, 0.624, P<0.01). The progression pattern prediction model showed an AUC of 0.762(95% CI, 0.643–0.882) and the hybrid model with clinical features showed an AUC of 0.794 (95% CI, 0.681–0.908), which can provide compensate information for clinical features-based model (AUC, 0.710; 95% CI, 0.582–0.839).

Conclusion

The CNN exhibits potential ability to stratify progression status in patients with EGFR mutation treated with first-line TKI, which might help make clinical decisions.

An Exploratory Study on the Stable Radiomics Features of Metastatic Small Pulmonary Nodules in Colorectal Cancer Patients

Objectives

To identify the relatively invariable radiomics features as essential characteristics during the growth process of metastatic pulmonary nodules with a diameter of 1 cm or smaller from colorectal cancer (CRC).

Methods

Three hundred and twenty lung nodules were enrolled in this study (200 CRC metastatic nodules in the training cohort, 60 benign nodules in the verification cohort 1, 60 CRC metastatic nodules in the verification cohort 2). All the nodules were divided into four groups according to the maximum diameter: 0 to 0.25 cm, 0.26 to 0.50 cm, 0.51 to 0.75 cm, 0.76 to 1.0 cm. These pulmonary nodules were manually outlined in computed tomography (CT) images with ITK-SNAP software, and 1724 radiomics features were extracted. Kruskal-Wallis test was performed to compare the four different levels of nodules. Cross-validation was used to verify the results. The Spearman rank correlation coefficient is calculated to evaluate the correlation between features.

Results

In training cohort, 90 features remained stable during the growth process of metastasis nodules. In verification cohort 1, 293 features remained stable during the growth process of benign nodules. In verification cohort 2, 118 features remained stable during the growth process of metastasis nodules. It is concluded that 20 features remained stable in metastatic nodules (training cohort and verification cohort 2) but not stable in benign nodules (verification cohort 1). Through the cross-validation (n=100), 11 features remained stable more than 90 times.

Conclusions

This study suggests that a small number of radiomics features from CRC metastatic pulmonary nodules remain relatively stable from small to large, and they do not remain stable in benign nodules. These stable features may reflect the essential characteristics of metastatic nodules and become a valuable point for identifying metastatic pulmonary nodules from benign nodules.